From e05c7df42f7928f61805c4fbc3de94d39cfbf564 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E0=A4=B8=E0=A4=AE=E0=A5=80=E0=A4=B0=20=E0=A4=B8=E0=A4=BF?= =?UTF-8?q?=E0=A4=82=E0=A4=B9=20Sameer=20Singh?= Date: Fri, 16 Sep 2022 06:52:51 +0530 Subject: [PATCH] Update Unicode support to Unicode version 15.0.0 * admin/unidata/BidiBrackets.txt * admin/unidata/BidiMirroring.txt * admin/unidata/Blocks.txt * admin/unidata/IVD_Sequences.txt * admin/unidata/IdnaMappingTable.txt * admin/unidata/NormalizationTest.txt * admin/unidata/PropertyValueAliases.txt * admin/unidata/ScriptExtensions.txt * admin/unidata/Scripts.txt * admin/unidata/SpecialCasing.txt * admin/unidata/UnicodeData.txt * admin/unidata/confusables.txt * admin/unidata/copyright.html * admin/unidata/emoji-data.txt * admin/unidata/emoji-sequences.txt * admin/unidata/emoji-test.txt * admin/unidata/emoji-zwj-sequences.txt * test/manual/BidiCharacterTest.txt: Updated files from Unicode 15.0. * admin/unidata/blocks.awk (name2alias): Add new scripts * admin/unidata/unidata-gen.el (unidata-file-alist): Add new ranges * lisp/international/fontset.el (script-representative-chars): Add new scripts. (otf-script-alist): Update from latest version. (setup-default-fontset): Add new scripts. * lisp/international/characters.el: Update syntax and category tables for new characters and scripts. (char-width-table): Update for changes in Unicode 15.0. * test/lisp/international/ucs-normalize-tests.el (ucs-normalize-tests--failing-lines-part1) (ucs-normalize-tests--failing-lines-part2): Update per the test results. * doc/lispref/nonascii.texi (Character Properties): Update Unicode version number. * etc/NEWS: Announce support for Unicode 15.0. --- admin/unidata/BidiBrackets.txt | 6 +- admin/unidata/BidiMirroring.txt | 8 +- admin/unidata/Blocks.txt | 21 +- admin/unidata/IVD_Sequences.txt | 6 +- admin/unidata/IdnaMappingTable.txt | 169 +++++++-- admin/unidata/NormalizationTest.txt | 92 ++++- admin/unidata/PropertyValueAliases.txt | 24 +- admin/unidata/ScriptExtensions.txt | 10 +- admin/unidata/Scripts.txt | 106 ++++-- admin/unidata/SpecialCasing.txt | 10 +- admin/unidata/UnicodeData.txt | 300 ++++++++++++++- admin/unidata/blocks.awk | 3 + admin/unidata/confusables.txt | 22 +- admin/unidata/copyright.html | 6 +- admin/unidata/emoji-data.txt | 73 ++-- admin/unidata/emoji-sequences.txt | 343 ++++++++++-------- admin/unidata/emoji-test.txt | 125 ++++--- admin/unidata/emoji-zwj-sequences.txt | 13 +- admin/unidata/unidata-gen.el | 10 +- doc/lispref/nonascii.texi | 2 +- etc/NEWS | 3 + lisp/international/characters.el | 62 +++- lisp/international/fontset.el | 8 + .../lisp/international/ucs-normalize-tests.el | 89 +++-- test/manual/BidiCharacterTest.txt | 12 +- 25 files changed, 1104 insertions(+), 419 deletions(-) diff --git a/admin/unidata/BidiBrackets.txt b/admin/unidata/BidiBrackets.txt index 89698f588a..e138e7f5be 100644 --- a/admin/unidata/BidiBrackets.txt +++ b/admin/unidata/BidiBrackets.txt @@ -1,6 +1,6 @@ -# BidiBrackets-14.0.0.txt -# Date: 2021-06-30, 23:59:00 GMT [AG, LI, KW] -# © 2021 Unicode®, Inc. +# BidiBrackets-15.0.0.txt +# Date: 2022-05-03, 18:42:00 GMT [AG, LI, KW] +# © 2022 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html # diff --git a/admin/unidata/BidiMirroring.txt b/admin/unidata/BidiMirroring.txt index bd8e2c5d00..5861d6e7f4 100644 --- a/admin/unidata/BidiMirroring.txt +++ b/admin/unidata/BidiMirroring.txt @@ -1,6 +1,6 @@ -# BidiMirroring-14.0.0.txt -# Date: 2021-08-08, 22:55:00 GMT [KW, RP] -# © 2021 Unicode®, Inc. +# BidiMirroring-15.0.0.txt +# Date: 2022-05-03, 18:47:00 GMT [KW, RP] +# © 2022 Unicode®, Inc. # For terms of use, see https://www.unicode.org/terms_of_use.html # # Unicode Character Database @@ -15,7 +15,7 @@ # value, for which there is another Unicode character that typically has a glyph # that is the mirror image of the original character's glyph. # -# The repertoire covered by the file is Unicode 14.0.0. +# The repertoire covered by the file is Unicode 15.0.0. # # The file contains a list of lines with mappings from one code point # to another one for character-based mirroring. diff --git a/admin/unidata/Blocks.txt b/admin/unidata/Blocks.txt index cc5d61988b..12684594c9 100644 --- a/admin/unidata/Blocks.txt +++ b/admin/unidata/Blocks.txt @@ -1,10 +1,10 @@ -# Blocks-14.0.0.txt -# Date: 2021-01-22, 23:29:00 GMT [KW] -# © 2021 Unicode®, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html +# Blocks-15.0.0.txt +# Date: 2022-01-28, 20:58:00 GMT [KW] +# © 2022 Unicode®, Inc. +# For terms of use, see https://www.unicode.org/terms_of_use.html # # Unicode Character Database -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see https://www.unicode.org/reports/tr44/ # # Format: # Start Code..End Code; Block Name @@ -15,7 +15,7 @@ # and underbars are ignored. # For example, "Latin Extended-A" and "latin extended a" are equivalent. # For more information on the comparison of property values, -# see UAX #44: http://www.unicode.org/reports/tr44/ +# see UAX #44: https://www.unicode.org/reports/tr44/ # # All block ranges start with a value where (cp MOD 16) = 0, # and end with a value where (cp MOD 16) = 15. In other words, @@ -241,6 +241,7 @@ FFF0..FFFF; Specials 10D00..10D3F; Hanifi Rohingya 10E60..10E7F; Rumi Numeral Symbols 10E80..10EBF; Yezidi +10EC0..10EFF; Arabic Extended-C 10F00..10F2F; Old Sogdian 10F30..10F6F; Sogdian 10F70..10FAF; Old Uyghur @@ -272,11 +273,13 @@ FFF0..FFFF; Specials 11A50..11AAF; Soyombo 11AB0..11ABF; Unified Canadian Aboriginal Syllabics Extended-A 11AC0..11AFF; Pau Cin Hau +11B00..11B5F; Devanagari Extended-A 11C00..11C6F; Bhaiksuki 11C70..11CBF; Marchen 11D00..11D5F; Masaram Gondi 11D60..11DAF; Gunjala Gondi 11EE0..11EFF; Makasar +11F00..11F5F; Kawi 11FB0..11FBF; Lisu Supplement 11FC0..11FFF; Tamil Supplement 12000..123FF; Cuneiform @@ -284,7 +287,7 @@ FFF0..FFFF; Specials 12480..1254F; Early Dynastic Cuneiform 12F90..12FFF; Cypro-Minoan 13000..1342F; Egyptian Hieroglyphs -13430..1343F; Egyptian Hieroglyph Format Controls +13430..1345F; Egyptian Hieroglyph Format Controls 14400..1467F; Anatolian Hieroglyphs 16800..16A3F; Bamum Supplement 16A40..16A6F; Mro @@ -309,6 +312,7 @@ FFF0..FFFF; Specials 1D000..1D0FF; Byzantine Musical Symbols 1D100..1D1FF; Musical Symbols 1D200..1D24F; Ancient Greek Musical Notation +1D2C0..1D2DF; Kaktovik Numerals 1D2E0..1D2FF; Mayan Numerals 1D300..1D35F; Tai Xuan Jing Symbols 1D360..1D37F; Counting Rod Numerals @@ -316,9 +320,11 @@ FFF0..FFFF; Specials 1D800..1DAAF; Sutton SignWriting 1DF00..1DFFF; Latin Extended-G 1E000..1E02F; Glagolitic Supplement +1E030..1E08F; Cyrillic Extended-D 1E100..1E14F; Nyiakeng Puachue Hmong 1E290..1E2BF; Toto 1E2C0..1E2FF; Wancho +1E4D0..1E4FF; Nag Mundari 1E7E0..1E7FF; Ethiopic Extended-B 1E800..1E8DF; Mende Kikakui 1E900..1E95F; Adlam @@ -348,6 +354,7 @@ FFF0..FFFF; Specials 2CEB0..2EBEF; CJK Unified Ideographs Extension F 2F800..2FA1F; CJK Compatibility Ideographs Supplement 30000..3134F; CJK Unified Ideographs Extension G +31350..323AF; CJK Unified Ideographs Extension H E0000..E007F; Tags E0100..E01EF; Variation Selectors Supplement F0000..FFFFF; Supplementary Private Use Area-A diff --git a/admin/unidata/IVD_Sequences.txt b/admin/unidata/IVD_Sequences.txt index 886d8519ab..86a4ab5138 100644 --- a/admin/unidata/IVD_Sequences.txt +++ b/admin/unidata/IVD_Sequences.txt @@ -2,6 +2,9 @@ # # History: # +# 2022-09-13 Registration of additional sequences in the Adobe-Japan1 +# collection. +# # 2020-11-06 Registration of additional sequences in the MSARG # collection. # @@ -32,7 +35,7 @@ # For more details on the IVD, see UTS #37: # https://www.unicode.org/reports/tr37/ # -# Copyright 2006-2020 Unicode, Inc. +# Copyright 2006-2022 Unicode, Inc. # For terms of use, see: https://www.unicode.org/copyright.html#8 # 3402 E0100; Adobe-Japan1; CID+13698 @@ -39337,4 +39340,5 @@ FA29 E0100; Adobe-Japan1; CID+8687 2EB71 E0101; Moji_Joho; MJ059252 2EB79 E0100; Moji_Joho; MJ059255 2EB79 E0101; Moji_Joho; MJ059256 +31350 E0100; Adobe-Japan1; CID+19130 # EOF diff --git a/admin/unidata/IdnaMappingTable.txt b/admin/unidata/IdnaMappingTable.txt index 1b862827ef..e4c0611792 100644 --- a/admin/unidata/IdnaMappingTable.txt +++ b/admin/unidata/IdnaMappingTable.txt @@ -1,13 +1,13 @@ # IdnaMappingTable.txt -# Date: 2021-07-10, 00:49:51 GMT -# © 2021 Unicode®, Inc. +# Date: 2022-05-02, 19:29:26 GMT +# © 2022 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. -# For terms of use, see http://www.unicode.org/terms_of_use.html +# For terms of use, see https://www.unicode.org/terms_of_use.html # # Unicode IDNA Compatible Preprocessing for UTS #46 -# Version: 14.0.0 +# Version: 15.0.0 # -# For documentation and usage, see http://www.unicode.org/reports/tr46 +# For documentation and usage, see https://www.unicode.org/reports/tr46 # 0000..002C ; disallowed_STD3_valid # 1.1 ..COMMA 002D..002E ; valid # 1.1 HYPHEN-MINUS..FULL STOP @@ -1278,7 +1278,8 @@ 0CE6..0CEF ; valid # 1.1 KANNADA DIGIT ZERO..KANNADA DIGIT NINE 0CF0 ; disallowed # NA 0CF1..0CF2 ; valid # 5.0 KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA -0CF3..0CFF ; disallowed # NA .. +0CF3 ; valid # 15.0 KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT +0CF4..0CFF ; disallowed # NA .. 0D00 ; valid # 10.0 MALAYALAM SIGN COMBINING ANUSVARA ABOVE 0D01 ; valid # 7.0 MALAYALAM SIGN CANDRABINDU 0D02..0D03 ; valid # 1.1 MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA @@ -1386,7 +1387,8 @@ 0EC6 ; valid # 1.1 LAO KO LA 0EC7 ; disallowed # NA 0EC8..0ECD ; valid # 1.1 LAO TONE MAI EK..LAO NIGGAHITA -0ECE..0ECF ; disallowed # NA .. +0ECE ; valid # 15.0 LAO YAMAKKAN +0ECF ; disallowed # NA 0ED0..0ED9 ; valid # 1.1 LAO DIGIT ZERO..LAO DIGIT NINE 0EDA..0EDB ; disallowed # NA .. 0EDC ; mapped ; 0EAB 0E99 # 1.1 LAO HO NO @@ -6206,7 +6208,8 @@ FFFE..FFFF ; disallowed # 1.1 .. 10EB0..10EB1 ; valid # 13.0 YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE -10EB2..10EFF ; disallowed # NA .. +10EB2..10EFC ; disallowed # NA .. +10EFD..10EFF ; valid # 15.0 ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; valid # 11.0 OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F1D..10F26 ; valid ; ; NV8 # 11.0 OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF 10F27 ; valid # 11.0 OLD SOGDIAN LIGATURE AYIN-DALETH @@ -6271,7 +6274,8 @@ FFFE..FFFF ; disallowed # 1.1 .. +1123F..11241 ; valid # 15.0 KHOJKI LETTER QA..KHOJKI VOWEL SIGN VOCALIC R +11242..1127F ; disallowed # NA .. 11280..11286 ; valid # 8.0 MULTANI LETTER A..MULTANI LETTER GA 11287 ; disallowed # NA 11288 ; valid # 8.0 MULTANI LETTER GHA @@ -6443,7 +6447,9 @@ FFFE..FFFF ; disallowed # 1.1 .. 11AB0..11ABF ; valid # 14.0 CANADIAN SYLLABICS NATTILIK HI..CANADIAN SYLLABICS SPA 11AC0..11AF8 ; valid # 7.0 PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL -11AF9..11BFF ; disallowed # NA .. +11AF9..11AFF ; disallowed # NA .. +11B00..11B09 ; valid ; ; NV8 # 15.0 DEVANAGARI HEAD MARK..DEVANAGARI SIGN MINDU +11B0A..11BFF ; disallowed # NA .. 11C00..11C08 ; valid # 9.0 BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C09 ; disallowed # NA 11C0A..11C36 ; valid # 9.0 BHAIKSUKI LETTER E..BHAIKSUKI VOWEL SIGN VOCALIC L @@ -6489,7 +6495,15 @@ FFFE..FFFF ; disallowed # 1.1 .. 11EE0..11EF6 ; valid # 11.0 MAKASAR LETTER KA..MAKASAR VOWEL SIGN O 11EF7..11EF8 ; valid ; ; NV8 # 11.0 MAKASAR PASSIMBANG..MAKASAR END OF SECTION -11EF9..11FAF ; disallowed # NA .. +11EF9..11EFF ; disallowed # NA .. +11F00..11F10 ; valid # 15.0 KAWI SIGN CANDRABINDU..KAWI LETTER O +11F11 ; disallowed # NA +11F12..11F3A ; valid # 15.0 KAWI LETTER KA..KAWI VOWEL SIGN VOCALIC R +11F3B..11F3D ; disallowed # NA .. +11F3E..11F42 ; valid # 15.0 KAWI VOWEL SIGN E..KAWI CONJOINER +11F43..11F4F ; valid ; ; NV8 # 15.0 KAWI DANDA..KAWI PUNCTUATION CLOSING SPIRAL +11F50..11F59 ; valid # 15.0 KAWI DIGIT ZERO..KAWI DIGIT NINE +11F5A..11FAF ; disallowed # NA .. 11FB0 ; valid # 13.0 LISU LETTER YHA 11FB1..11FBF ; disallowed # NA .. 11FC0..11FF1 ; valid ; ; NV8 # 12.0 TAMIL FRACTION ONE THREE-HUNDRED-AND-TWENTIETH..TAMIL SIGN VAKAIYARAA @@ -6511,9 +6525,11 @@ FFFE..FFFF ; disallowed # 1.1 .. 13000..1342E ; valid # 5.2 EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 -1342F ; disallowed # NA +1342F ; valid # 15.0 EGYPTIAN HIEROGLYPH V011D 13430..13438 ; disallowed # 12.0 EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END SEGMENT -13439..143FF ; disallowed # NA .. +13439..1343F ; disallowed # 15.0 EGYPTIAN HIEROGLYPH INSERT AT MIDDLE..EGYPTIAN HIEROGLYPH END WALLED ENCLOSURE +13440..13455 ; valid # 15.0 EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY..EGYPTIAN HIEROGLYPH MODIFIER DAMAGED +13456..143FF ; disallowed # NA .. 14400..14646 ; valid # 8.0 ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530 14647..167FF ; disallowed # NA .. 16800..16A38 ; valid # 6.0 BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ @@ -6615,9 +6631,13 @@ FFFE..FFFF ; disallowed # 1.1 .. +1B123..1B131 ; disallowed # NA .. +1B132 ; valid # 15.0 HIRAGANA LETTER SMALL KO +1B133..1B14F ; disallowed # NA .. 1B150..1B152 ; valid # 12.0 HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO -1B153..1B163 ; disallowed # NA .. +1B153..1B154 ; disallowed # NA .. +1B155 ; valid # 15.0 KATAKANA LETTER SMALL KO +1B156..1B163 ; disallowed # NA .. 1B164..1B167 ; valid # 12.0 KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N 1B168..1B16F ; disallowed # NA .. 1B170..1B2FB ; valid # 10.0 NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB @@ -6668,7 +6688,9 @@ FFFE..FFFF ; disallowed # 1.1 .. 1D200..1D245 ; valid ; ; NV8 # 4.1 GREEK VOCAL NOTATION SYMBOL-1..GREEK MUSICAL LEIMMA -1D246..1D2DF ; disallowed # NA .. +1D246..1D2BF ; disallowed # NA .. +1D2C0..1D2D3 ; valid ; ; NV8 # 15.0 KAKTOVIK NUMERAL ZERO..KAKTOVIK NUMERAL NINETEEN +1D2D4..1D2DF ; disallowed # NA .. 1D2E0..1D2F3 ; valid ; ; NV8 # 11.0 MAYAN NUMERAL ZERO..MAYAN NUMERAL NINETEEN 1D2F4..1D2FF ; disallowed # NA .. 1D300..1D356 ; valid ; ; NV8 # 4.0 MONOGRAM FOR EARTH..TETRAGRAM FOR FOSTERING @@ -7701,7 +7723,9 @@ FFFE..FFFF ; disallowed # 1.1 .. 1DF00..1DF1E ; valid # 14.0 LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER S WITH CURL -1DF1F..1DFFF ; disallowed # NA .. +1DF1F..1DF24 ; disallowed # NA .. +1DF25..1DF2A ; valid # 15.0 LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK +1DF2B..1DFFF ; disallowed # NA .. 1E000..1E006 ; valid # 9.0 COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE 1E007 ; disallowed # NA 1E008..1E018 ; valid # 9.0 COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU @@ -7711,7 +7735,72 @@ FFFE..FFFF ; disallowed # 1.1 1E026..1E02A ; valid # 9.0 COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA -1E02B..1E0FF ; disallowed # NA .. +1E02B..1E02F ; disallowed # NA .. +1E030 ; mapped ; 0430 # 15.0 MODIFIER LETTER CYRILLIC SMALL A +1E031 ; mapped ; 0431 # 15.0 MODIFIER LETTER CYRILLIC SMALL BE +1E032 ; mapped ; 0432 # 15.0 MODIFIER LETTER CYRILLIC SMALL VE +1E033 ; mapped ; 0433 # 15.0 MODIFIER LETTER CYRILLIC SMALL GHE +1E034 ; mapped ; 0434 # 15.0 MODIFIER LETTER CYRILLIC SMALL DE +1E035 ; mapped ; 0435 # 15.0 MODIFIER LETTER CYRILLIC SMALL IE +1E036 ; mapped ; 0436 # 15.0 MODIFIER LETTER CYRILLIC SMALL ZHE +1E037 ; mapped ; 0437 # 15.0 MODIFIER LETTER CYRILLIC SMALL ZE +1E038 ; mapped ; 0438 # 15.0 MODIFIER LETTER CYRILLIC SMALL I +1E039 ; mapped ; 043A # 15.0 MODIFIER LETTER CYRILLIC SMALL KA +1E03A ; mapped ; 043B # 15.0 MODIFIER LETTER CYRILLIC SMALL EL +1E03B ; mapped ; 043C # 15.0 MODIFIER LETTER CYRILLIC SMALL EM +1E03C ; mapped ; 043E # 15.0 MODIFIER LETTER CYRILLIC SMALL O +1E03D ; mapped ; 043F # 15.0 MODIFIER LETTER CYRILLIC SMALL PE +1E03E ; mapped ; 0440 # 15.0 MODIFIER LETTER CYRILLIC SMALL ER +1E03F ; mapped ; 0441 # 15.0 MODIFIER LETTER CYRILLIC SMALL ES +1E040 ; mapped ; 0442 # 15.0 MODIFIER LETTER CYRILLIC SMALL TE +1E041 ; mapped ; 0443 # 15.0 MODIFIER LETTER CYRILLIC SMALL U +1E042 ; mapped ; 0444 # 15.0 MODIFIER LETTER CYRILLIC SMALL EF +1E043 ; mapped ; 0445 # 15.0 MODIFIER LETTER CYRILLIC SMALL HA +1E044 ; mapped ; 0446 # 15.0 MODIFIER LETTER CYRILLIC SMALL TSE +1E045 ; mapped ; 0447 # 15.0 MODIFIER LETTER CYRILLIC SMALL CHE +1E046 ; mapped ; 0448 # 15.0 MODIFIER LETTER CYRILLIC SMALL SHA +1E047 ; mapped ; 044B # 15.0 MODIFIER LETTER CYRILLIC SMALL YERU +1E048 ; mapped ; 044D # 15.0 MODIFIER LETTER CYRILLIC SMALL E +1E049 ; mapped ; 044E # 15.0 MODIFIER LETTER CYRILLIC SMALL YU +1E04A ; mapped ; A689 # 15.0 MODIFIER LETTER CYRILLIC SMALL DZZE +1E04B ; mapped ; 04D9 # 15.0 MODIFIER LETTER CYRILLIC SMALL SCHWA +1E04C ; mapped ; 0456 # 15.0 MODIFIER LETTER CYRILLIC SMALL BYELORUSSIAN-UKRAINIAN I +1E04D ; mapped ; 0458 # 15.0 MODIFIER LETTER CYRILLIC SMALL JE +1E04E ; mapped ; 04E9 # 15.0 MODIFIER LETTER CYRILLIC SMALL BARRED O +1E04F ; mapped ; 04AF # 15.0 MODIFIER LETTER CYRILLIC SMALL STRAIGHT U +1E050 ; mapped ; 04CF # 15.0 MODIFIER LETTER CYRILLIC SMALL PALOCHKA +1E051 ; mapped ; 0430 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER A +1E052 ; mapped ; 0431 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER BE +1E053 ; mapped ; 0432 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER VE +1E054 ; mapped ; 0433 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER GHE +1E055 ; mapped ; 0434 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER DE +1E056 ; mapped ; 0435 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER IE +1E057 ; mapped ; 0436 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER ZHE +1E058 ; mapped ; 0437 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER ZE +1E059 ; mapped ; 0438 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER I +1E05A ; mapped ; 043A # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER KA +1E05B ; mapped ; 043B # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER EL +1E05C ; mapped ; 043E # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER O +1E05D ; mapped ; 043F # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER PE +1E05E ; mapped ; 0441 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER ES +1E05F ; mapped ; 0443 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER U +1E060 ; mapped ; 0444 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER EF +1E061 ; mapped ; 0445 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER HA +1E062 ; mapped ; 0446 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER TSE +1E063 ; mapped ; 0447 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER CHE +1E064 ; mapped ; 0448 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER SHA +1E065 ; mapped ; 044A # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER HARD SIGN +1E066 ; mapped ; 044B # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER YERU +1E067 ; mapped ; 0491 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER GHE WITH UPTURN +1E068 ; mapped ; 0456 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER BYELORUSSIAN-UKRAINIAN I +1E069 ; mapped ; 0455 # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER DZE +1E06A ; mapped ; 045F # 15.0 CYRILLIC SUBSCRIPT SMALL LETTER DZHE +1E06B ; mapped ; 04AB # 15.0 MODIFIER LETTER CYRILLIC SMALL ES WITH DESCENDER +1E06C ; mapped ; A651 # 15.0 MODIFIER LETTER CYRILLIC SMALL YERU WITH BACK YER +1E06D ; mapped ; 04B1 # 15.0 MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE +1E06E..1E08E ; disallowed # NA .. +1E08F ; valid # 15.0 COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I +1E090..1E0FF ; disallowed # NA .. 1E100..1E12C ; valid # 12.0 NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W 1E12D..1E12F ; disallowed # NA .. 1E130..1E13D ; valid # 12.0 NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER @@ -7726,7 +7815,9 @@ FFFE..FFFF ; disallowed # 1.1 .. 1E2FF ; valid ; ; NV8 # 12.0 WANCHO NGUN SIGN -1E300..1E7DF ; disallowed # NA .. +1E300..1E4CF ; disallowed # NA .. +1E4D0..1E4F9 ; valid # 15.0 NAG MUNDARI LETTER O..NAG MUNDARI DIGIT NINE +1E4FA..1E7DF ; disallowed # NA .. 1E7E0..1E7E6 ; valid # 14.0 ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E7 ; disallowed # NA 1E7E8..1E7EB ; valid # 14.0 ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE @@ -8213,7 +8304,8 @@ FFFE..FFFF ; disallowed # 1.1 .. +1F6D8..1F6DB ; disallowed # NA .. +1F6DC ; valid ; ; NV8 # 15.0 WIRELESS 1F6DD..1F6DF ; valid ; ; NV8 # 14.0 PLAYGROUND SLIDE..RING BUOY 1F6E0..1F6EC ; valid ; ; NV8 # 7.0 HAMMER AND WRENCH..AIRPLANE ARRIVING 1F6ED..1F6EF ; disallowed # NA .. @@ -8225,10 +8317,13 @@ FFFE..FFFF ; disallowed # 1.1 .. 1F700..1F773 ; valid ; ; NV8 # 6.0 ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE -1F774..1F77F ; disallowed # NA .. +1F774..1F776 ; valid ; ; NV8 # 15.0 LOT OF FORTUNE..LUNAR ECLIPSE +1F777..1F77A ; disallowed # NA .. +1F77B..1F77F ; valid ; ; NV8 # 15.0 HAUMEA..ORCUS 1F780..1F7D4 ; valid ; ; NV8 # 7.0 BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..HEAVY TWELVE POINTED PINWHEEL STAR 1F7D5..1F7D8 ; valid ; ; NV8 # 11.0 CIRCLED TRIANGLE..NEGATIVE CIRCLED SQUARE -1F7D9..1F7DF ; disallowed # NA .. +1F7D9 ; valid ; ; NV8 # 15.0 NINE POINTED WHITE STAR +1F7DA..1F7DF ; disallowed # NA .. 1F7E0..1F7EB ; valid ; ; NV8 # 12.0 LARGE ORANGE CIRCLE..LARGE BROWN SQUARE 1F7EC..1F7EF ; disallowed # NA .. 1F7F0 ; valid ; ; NV8 # 14.0 HEAVY EQUALS SIGN @@ -8295,30 +8390,37 @@ FFFE..FFFF ; disallowed # 1.1 .. 1FA70..1FA73 ; valid ; ; NV8 # 12.0 BALLET SHOES..SHORTS 1FA74 ; valid ; ; NV8 # 13.0 THONG SANDAL -1FA75..1FA77 ; disallowed # NA .. +1FA75..1FA77 ; valid ; ; NV8 # 15.0 LIGHT BLUE HEART..PINK HEART 1FA78..1FA7A ; valid ; ; NV8 # 12.0 DROP OF BLOOD..STETHOSCOPE 1FA7B..1FA7C ; valid ; ; NV8 # 14.0 X-RAY..CRUTCH 1FA7D..1FA7F ; disallowed # NA .. 1FA80..1FA82 ; valid ; ; NV8 # 12.0 YO-YO..PARACHUTE 1FA83..1FA86 ; valid ; ; NV8 # 13.0 BOOMERANG..NESTING DOLLS -1FA87..1FA8F ; disallowed # NA .. +1FA87..1FA88 ; valid ; ; NV8 # 15.0 MARACAS..FLUTE +1FA89..1FA8F ; disallowed # NA .. 1FA90..1FA95 ; valid ; ; NV8 # 12.0 RINGED PLANET..BANJO 1FA96..1FAA8 ; valid ; ; NV8 # 13.0 MILITARY HELMET..ROCK 1FAA9..1FAAC ; valid ; ; NV8 # 14.0 MIRROR BALL..HAMSA -1FAAD..1FAAF ; disallowed # NA .. +1FAAD..1FAAF ; valid ; ; NV8 # 15.0 FOLDING HAND FAN..KHANDA 1FAB0..1FAB6 ; valid ; ; NV8 # 13.0 FLY..FEATHER 1FAB7..1FABA ; valid ; ; NV8 # 14.0 LOTUS..NEST WITH EGGS -1FABB..1FABF ; disallowed # NA .. +1FABB..1FABD ; valid ; ; NV8 # 15.0 HYACINTH..WING +1FABE ; disallowed # NA +1FABF ; valid ; ; NV8 # 15.0 GOOSE 1FAC0..1FAC2 ; valid ; ; NV8 # 13.0 ANATOMICAL HEART..PEOPLE HUGGING 1FAC3..1FAC5 ; valid ; ; NV8 # 14.0 PREGNANT MAN..PERSON WITH CROWN -1FAC6..1FACF ; disallowed # NA .. +1FAC6..1FACD ; disallowed # NA .. +1FACE..1FACF ; valid ; ; NV8 # 15.0 MOOSE..DONKEY 1FAD0..1FAD6 ; valid ; ; NV8 # 13.0 BLUEBERRIES..TEAPOT 1FAD7..1FAD9 ; valid ; ; NV8 # 14.0 POURING LIQUID..JAR -1FADA..1FADF ; disallowed # NA .. +1FADA..1FADB ; valid ; ; NV8 # 15.0 GINGER ROOT..PEA POD +1FADC..1FADF ; disallowed # NA .. 1FAE0..1FAE7 ; valid ; ; NV8 # 14.0 MELTING FACE..BUBBLES -1FAE8..1FAEF ; disallowed # NA .. +1FAE8 ; valid ; ; NV8 # 15.0 SHAKING FACE +1FAE9..1FAEF ; disallowed # NA .. 1FAF0..1FAF6 ; valid ; ; NV8 # 14.0 HAND WITH INDEX FINGER AND THUMB CROSSED..HEART HANDS -1FAF7..1FAFF ; disallowed # NA .. +1FAF7..1FAF8 ; valid ; ; NV8 # 15.0 LEFTWARDS PUSHING HAND..RIGHTWARDS PUSHING HAND +1FAF9..1FAFF ; disallowed # NA .. 1FB00..1FB92 ; valid ; ; NV8 # 13.0 BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB93 ; disallowed # NA 1FB94..1FBCA ; valid ; ; NV8 # 13.0 LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON @@ -8341,7 +8443,8 @@ FFFE..FFFF ; disallowed # 1.1 .. 2A700..2B734 ; valid # 5.2 CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 2B735..2B738 ; valid # 14.0 CJK UNIFIED IDEOGRAPH-2B735..CJK UNIFIED IDEOGRAPH-2B738 -2B739..2B73F ; disallowed # NA .. +2B739 ; valid # 15.0 CJK UNIFIED IDEOGRAPH-2B739 +2B73A..2B73F ; disallowed # NA .. 2B740..2B81D ; valid # 6.0 CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B81E..2B81F ; disallowed # NA .. 2B820..2CEA1 ; valid # 8.0 CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 @@ -8883,7 +8986,9 @@ FFFE..FFFF ; disallowed # 1.1 .. 2FFFE..2FFFF ; disallowed # 2.0 .. 30000..3134A ; valid # 13.0 CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A -3134B..3FFFD ; disallowed # NA .. +3134B..3134F ; disallowed # NA .. +31350..323AF ; valid # 15.0 CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF +323B0..3FFFD ; disallowed # NA .. 3FFFE..3FFFF ; disallowed # 2.0 .. 40000..4FFFD ; disallowed # NA .. 4FFFE..4FFFF ; disallowed # 2.0 .. diff --git a/admin/unidata/NormalizationTest.txt b/admin/unidata/NormalizationTest.txt index 302c35f37c..e75b4801c9 100644 --- a/admin/unidata/NormalizationTest.txt +++ b/admin/unidata/NormalizationTest.txt @@ -1,11 +1,11 @@ -# NormalizationTest-14.0.0.txt -# Date: 2021-05-28, 21:49:12 GMT -# © 2021 Unicode®, Inc. +# NormalizationTest-15.0.0.txt +# Date: 2022-04-02, 01:29:09 GMT +# © 2022 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. -# For terms of use, see http://www.unicode.org/terms_of_use.html +# For terms of use, see https://www.unicode.org/terms_of_use.html # # Unicode Character Database -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see https://www.unicode.org/reports/tr44/ # # Normalization Test Suite # Format: @@ -16208,6 +16208,68 @@ FFEE;FFEE;FFEE;25CB;25CB; # (￮; ￮; ￮; ○; ○; ) HALFWIDTH WHITE CIRCLE 1D7FD;1D7FD;1D7FD;0037;0037; # (𝟽; 𝟽; 𝟽; 7; 7; ) MATHEMATICAL MONOSPACE DIGIT SEVEN 1D7FE;1D7FE;1D7FE;0038;0038; # (𝟾; 𝟾; 𝟾; 8; 8; ) MATHEMATICAL MONOSPACE DIGIT EIGHT 1D7FF;1D7FF;1D7FF;0039;0039; # (𝟿; 𝟿; 𝟿; 9; 9; ) MATHEMATICAL MONOSPACE DIGIT NINE +1E030;1E030;1E030;0430;0430; # (𞀰; 𞀰; 𞀰; а; а; ) MODIFIER LETTER CYRILLIC SMALL A +1E031;1E031;1E031;0431;0431; # (𞀱; 𞀱; 𞀱; б; б; ) MODIFIER LETTER CYRILLIC SMALL BE +1E032;1E032;1E032;0432;0432; # (𞀲; 𞀲; 𞀲; в; в; ) MODIFIER LETTER CYRILLIC SMALL VE +1E033;1E033;1E033;0433;0433; # (𞀳; 𞀳; 𞀳; г; г; ) MODIFIER LETTER CYRILLIC SMALL GHE +1E034;1E034;1E034;0434;0434; # (𞀴; 𞀴; 𞀴; д; д; ) MODIFIER LETTER CYRILLIC SMALL DE +1E035;1E035;1E035;0435;0435; # (𞀵; 𞀵; 𞀵; е; е; ) MODIFIER LETTER CYRILLIC SMALL IE +1E036;1E036;1E036;0436;0436; # (𞀶; 𞀶; 𞀶; ж; ж; ) MODIFIER LETTER CYRILLIC SMALL ZHE +1E037;1E037;1E037;0437;0437; # (𞀷; 𞀷; 𞀷; з; з; ) MODIFIER LETTER CYRILLIC SMALL ZE +1E038;1E038;1E038;0438;0438; # (𞀸; 𞀸; 𞀸; и; и; ) MODIFIER LETTER CYRILLIC SMALL I +1E039;1E039;1E039;043A;043A; # (𞀹; 𞀹; 𞀹; к; к; ) MODIFIER LETTER CYRILLIC SMALL KA +1E03A;1E03A;1E03A;043B;043B; # (𞀺; 𞀺; 𞀺; л; л; ) MODIFIER LETTER CYRILLIC SMALL EL +1E03B;1E03B;1E03B;043C;043C; # (𞀻; 𞀻; 𞀻; м; м; ) MODIFIER LETTER CYRILLIC SMALL EM +1E03C;1E03C;1E03C;043E;043E; # (𞀼; 𞀼; 𞀼; о; о; ) MODIFIER LETTER CYRILLIC SMALL O +1E03D;1E03D;1E03D;043F;043F; # (𞀽; 𞀽; 𞀽; п; п; ) MODIFIER LETTER CYRILLIC SMALL PE +1E03E;1E03E;1E03E;0440;0440; # (𞀾; 𞀾; 𞀾; р; р; ) MODIFIER LETTER CYRILLIC SMALL ER +1E03F;1E03F;1E03F;0441;0441; # (𞀿; 𞀿; 𞀿; с; с; ) MODIFIER LETTER CYRILLIC SMALL ES +1E040;1E040;1E040;0442;0442; # (𞁀; 𞁀; 𞁀; т; т; ) MODIFIER LETTER CYRILLIC SMALL TE +1E041;1E041;1E041;0443;0443; # (𞁁; 𞁁; 𞁁; у; у; ) MODIFIER LETTER CYRILLIC SMALL U +1E042;1E042;1E042;0444;0444; # (𞁂; 𞁂; 𞁂; ф; ф; ) MODIFIER LETTER CYRILLIC SMALL EF +1E043;1E043;1E043;0445;0445; # (𞁃; 𞁃; 𞁃; х; х; ) MODIFIER LETTER CYRILLIC SMALL HA +1E044;1E044;1E044;0446;0446; # (𞁄; 𞁄; 𞁄; ц; ц; ) MODIFIER LETTER CYRILLIC SMALL TSE +1E045;1E045;1E045;0447;0447; # (𞁅; 𞁅; 𞁅; ч; ч; ) MODIFIER LETTER CYRILLIC SMALL CHE +1E046;1E046;1E046;0448;0448; # (𞁆; 𞁆; 𞁆; ш; ш; ) MODIFIER LETTER CYRILLIC SMALL SHA +1E047;1E047;1E047;044B;044B; # (𞁇; 𞁇; 𞁇; ы; ы; ) MODIFIER LETTER CYRILLIC SMALL YERU +1E048;1E048;1E048;044D;044D; # (𞁈; 𞁈; 𞁈; э; э; ) MODIFIER LETTER CYRILLIC SMALL E +1E049;1E049;1E049;044E;044E; # (𞁉; 𞁉; 𞁉; ю; ю; ) MODIFIER LETTER CYRILLIC SMALL YU +1E04A;1E04A;1E04A;A689;A689; # (𞁊; 𞁊; 𞁊; ꚉ; ꚉ; ) MODIFIER LETTER CYRILLIC SMALL DZZE +1E04B;1E04B;1E04B;04D9;04D9; # (𞁋; 𞁋; 𞁋; ә; ә; ) MODIFIER LETTER CYRILLIC SMALL SCHWA +1E04C;1E04C;1E04C;0456;0456; # (𞁌; 𞁌; 𞁌; і; і; ) MODIFIER LETTER CYRILLIC SMALL BYELORUSSIAN-UKRAINIAN I +1E04D;1E04D;1E04D;0458;0458; # (𞁍; 𞁍; 𞁍; ј; ј; ) MODIFIER LETTER CYRILLIC SMALL JE +1E04E;1E04E;1E04E;04E9;04E9; # (𞁎; 𞁎; 𞁎; ө; ө; ) MODIFIER LETTER CYRILLIC SMALL BARRED O +1E04F;1E04F;1E04F;04AF;04AF; # (𞁏; 𞁏; 𞁏; ү; ү; ) MODIFIER LETTER CYRILLIC SMALL STRAIGHT U +1E050;1E050;1E050;04CF;04CF; # (𞁐; 𞁐; 𞁐; ӏ; ӏ; ) MODIFIER LETTER CYRILLIC SMALL PALOCHKA +1E051;1E051;1E051;0430;0430; # (𞁑; 𞁑; 𞁑; а; а; ) CYRILLIC SUBSCRIPT SMALL LETTER A +1E052;1E052;1E052;0431;0431; # (𞁒; 𞁒; 𞁒; б; б; ) CYRILLIC SUBSCRIPT SMALL LETTER BE +1E053;1E053;1E053;0432;0432; # (𞁓; 𞁓; 𞁓; в; в; ) CYRILLIC SUBSCRIPT SMALL LETTER VE +1E054;1E054;1E054;0433;0433; # (𞁔; 𞁔; 𞁔; г; г; ) CYRILLIC SUBSCRIPT SMALL LETTER GHE +1E055;1E055;1E055;0434;0434; # (𞁕; 𞁕; 𞁕; д; д; ) CYRILLIC SUBSCRIPT SMALL LETTER DE +1E056;1E056;1E056;0435;0435; # (𞁖; 𞁖; 𞁖; е; е; ) CYRILLIC SUBSCRIPT SMALL LETTER IE +1E057;1E057;1E057;0436;0436; # (𞁗; 𞁗; 𞁗; ж; ж; ) CYRILLIC SUBSCRIPT SMALL LETTER ZHE +1E058;1E058;1E058;0437;0437; # (𞁘; 𞁘; 𞁘; з; з; ) CYRILLIC SUBSCRIPT SMALL LETTER ZE +1E059;1E059;1E059;0438;0438; # (𞁙; 𞁙; 𞁙; и; и; ) CYRILLIC SUBSCRIPT SMALL LETTER I +1E05A;1E05A;1E05A;043A;043A; # (𞁚; 𞁚; 𞁚; к; к; ) CYRILLIC SUBSCRIPT SMALL LETTER KA +1E05B;1E05B;1E05B;043B;043B; # (𞁛; 𞁛; 𞁛; л; л; ) CYRILLIC SUBSCRIPT SMALL LETTER EL +1E05C;1E05C;1E05C;043E;043E; # (𞁜; 𞁜; 𞁜; о; о; ) CYRILLIC SUBSCRIPT SMALL LETTER O +1E05D;1E05D;1E05D;043F;043F; # (𞁝; 𞁝; 𞁝; п; п; ) CYRILLIC SUBSCRIPT SMALL LETTER PE +1E05E;1E05E;1E05E;0441;0441; # (𞁞; 𞁞; 𞁞; с; с; ) CYRILLIC SUBSCRIPT SMALL LETTER ES +1E05F;1E05F;1E05F;0443;0443; # (𞁟; 𞁟; 𞁟; у; у; ) CYRILLIC SUBSCRIPT SMALL LETTER U +1E060;1E060;1E060;0444;0444; # (𞁠; 𞁠; 𞁠; ф; ф; ) CYRILLIC SUBSCRIPT SMALL LETTER EF +1E061;1E061;1E061;0445;0445; # (𞁡; 𞁡; 𞁡; х; х; ) CYRILLIC SUBSCRIPT SMALL LETTER HA +1E062;1E062;1E062;0446;0446; # (𞁢; 𞁢; 𞁢; ц; ц; ) CYRILLIC SUBSCRIPT SMALL LETTER TSE +1E063;1E063;1E063;0447;0447; # (𞁣; 𞁣; 𞁣; ч; ч; ) CYRILLIC SUBSCRIPT SMALL LETTER CHE +1E064;1E064;1E064;0448;0448; # (𞁤; 𞁤; 𞁤; ш; ш; ) CYRILLIC SUBSCRIPT SMALL LETTER SHA +1E065;1E065;1E065;044A;044A; # (𞁥; 𞁥; 𞁥; ъ; ъ; ) CYRILLIC SUBSCRIPT SMALL LETTER HARD SIGN +1E066;1E066;1E066;044B;044B; # (𞁦; 𞁦; 𞁦; ы; ы; ) CYRILLIC SUBSCRIPT SMALL LETTER YERU +1E067;1E067;1E067;0491;0491; # (𞁧; 𞁧; 𞁧; ґ; ґ; ) CYRILLIC SUBSCRIPT SMALL LETTER GHE WITH UPTURN +1E068;1E068;1E068;0456;0456; # (𞁨; 𞁨; 𞁨; і; і; ) CYRILLIC SUBSCRIPT SMALL LETTER BYELORUSSIAN-UKRAINIAN I +1E069;1E069;1E069;0455;0455; # (𞁩; 𞁩; 𞁩; ѕ; ѕ; ) CYRILLIC SUBSCRIPT SMALL LETTER DZE +1E06A;1E06A;1E06A;045F;045F; # (𞁪; 𞁪; 𞁪; џ; џ; ) CYRILLIC SUBSCRIPT SMALL LETTER DZHE +1E06B;1E06B;1E06B;04AB;04AB; # (𞁫; 𞁫; 𞁫; ҫ; ҫ; ) MODIFIER LETTER CYRILLIC SMALL ES WITH DESCENDER +1E06C;1E06C;1E06C;A651;A651; # (𞁬; 𞁬; 𞁬; ꙑ; ꙑ; ) MODIFIER LETTER CYRILLIC SMALL YERU WITH BACK YER +1E06D;1E06D;1E06D;04B1;04B1; # (𞁭; 𞁭; 𞁭; ұ; ұ; ) MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1EE00;1EE00;1EE00;0627;0627; # (𞸀; 𞸀; 𞸀; ا; ا; ) ARABIC MATHEMATICAL ALEF 1EE01;1EE01;1EE01;0628;0628; # (𞸁; 𞸁; 𞸁; ب; ب; ) ARABIC MATHEMATICAL BEH 1EE02;1EE02;1EE02;062C;062C; # (𞸂; 𞸂; 𞸂; ج; ج; ) ARABIC MATHEMATICAL JEEM @@ -18496,6 +18558,12 @@ FFEE;FFEE;FFEE;25CB;25CB; # (￮; ￮; ￮; ○; ○; ) HALFWIDTH WHITE CIRCLE 0061 10EAB 0315 0300 05AE 0062;0061 05AE 10EAB 0300 0315 0062;0061 05AE 10EAB 0300 0315 0062;0061 05AE 10EAB 0300 0315 0062;0061 05AE 10EAB 0300 0315 0062; # (a◌𐺫◌̕◌̀◌֮b; a◌֮◌𐺫◌̀◌̕b; a◌֮◌𐺫◌̀◌̕b; a◌֮◌𐺫◌̀◌̕b; a◌֮◌𐺫◌̀◌̕b; ) LATIN SMALL LETTER A, YEZIDI COMBINING HAMZA MARK, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, LATIN SMALL LETTER B 0061 0315 0300 05AE 10EAC 0062;00E0 05AE 10EAC 0315 0062;0061 05AE 0300 10EAC 0315 0062;00E0 05AE 10EAC 0315 0062;0061 05AE 0300 10EAC 0315 0062; # (a◌̕◌̀◌֮◌𐺬b; à◌֮◌𐺬◌̕b; a◌֮◌̀◌𐺬◌̕b; à◌֮◌𐺬◌̕b; a◌֮◌̀◌𐺬◌̕b; ) LATIN SMALL LETTER A, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, YEZIDI COMBINING MADDA MARK, LATIN SMALL LETTER B 0061 10EAC 0315 0300 05AE 0062;0061 05AE 10EAC 0300 0315 0062;0061 05AE 10EAC 0300 0315 0062;0061 05AE 10EAC 0300 0315 0062;0061 05AE 10EAC 0300 0315 0062; # (a◌𐺬◌̕◌̀◌֮b; a◌֮◌𐺬◌̀◌̕b; a◌֮◌𐺬◌̀◌̕b; a◌֮◌𐺬◌̀◌̕b; a◌֮◌𐺬◌̀◌̕b; ) LATIN SMALL LETTER A, YEZIDI COMBINING MADDA MARK, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, LATIN SMALL LETTER B +0061 059A 0316 1DFA 10EFD 0062;0061 1DFA 0316 10EFD 059A 0062;0061 1DFA 0316 10EFD 059A 0062;0061 1DFA 0316 10EFD 059A 0062;0061 1DFA 0316 10EFD 059A 0062; # (a◌֚◌̖◌᷺◌𐻽b; a◌᷺◌̖◌𐻽◌֚b; a◌᷺◌̖◌𐻽◌֚b; a◌᷺◌̖◌𐻽◌֚b; a◌᷺◌̖◌𐻽◌֚b; ) LATIN SMALL LETTER A, HEBREW ACCENT YETIV, COMBINING GRAVE ACCENT BELOW, COMBINING DOT BELOW LEFT, ARABIC SMALL LOW WORD SAKTA, LATIN SMALL LETTER B +0061 10EFD 059A 0316 1DFA 0062;0061 1DFA 10EFD 0316 059A 0062;0061 1DFA 10EFD 0316 059A 0062;0061 1DFA 10EFD 0316 059A 0062;0061 1DFA 10EFD 0316 059A 0062; # (a◌𐻽◌֚◌̖◌᷺b; a◌᷺◌𐻽◌̖◌֚b; a◌᷺◌𐻽◌̖◌֚b; a◌᷺◌𐻽◌̖◌֚b; a◌᷺◌𐻽◌̖◌֚b; ) LATIN SMALL LETTER A, ARABIC SMALL LOW WORD SAKTA, HEBREW ACCENT YETIV, COMBINING GRAVE ACCENT BELOW, COMBINING DOT BELOW LEFT, LATIN SMALL LETTER B +0061 059A 0316 1DFA 10EFE 0062;0061 1DFA 0316 10EFE 059A 0062;0061 1DFA 0316 10EFE 059A 0062;0061 1DFA 0316 10EFE 059A 0062;0061 1DFA 0316 10EFE 059A 0062; # (a◌֚◌̖◌᷺◌𐻾b; a◌᷺◌̖◌𐻾◌֚b; a◌᷺◌̖◌𐻾◌֚b; a◌᷺◌̖◌𐻾◌֚b; a◌᷺◌̖◌𐻾◌֚b; ) LATIN SMALL LETTER A, HEBREW ACCENT YETIV, COMBINING GRAVE ACCENT BELOW, COMBINING DOT BELOW LEFT, ARABIC SMALL LOW WORD QASR, LATIN SMALL LETTER B +0061 10EFE 059A 0316 1DFA 0062;0061 1DFA 10EFE 0316 059A 0062;0061 1DFA 10EFE 0316 059A 0062;0061 1DFA 10EFE 0316 059A 0062;0061 1DFA 10EFE 0316 059A 0062; # (a◌𐻾◌֚◌̖◌᷺b; a◌᷺◌𐻾◌̖◌֚b; a◌᷺◌𐻾◌̖◌֚b; a◌᷺◌𐻾◌̖◌֚b; a◌᷺◌𐻾◌̖◌֚b; ) LATIN SMALL LETTER A, ARABIC SMALL LOW WORD QASR, HEBREW ACCENT YETIV, COMBINING GRAVE ACCENT BELOW, COMBINING DOT BELOW LEFT, LATIN SMALL LETTER B +0061 059A 0316 1DFA 10EFF 0062;0061 1DFA 0316 10EFF 059A 0062;0061 1DFA 0316 10EFF 059A 0062;0061 1DFA 0316 10EFF 059A 0062;0061 1DFA 0316 10EFF 059A 0062; # (a◌֚◌̖◌᷺◌𐻿b; a◌᷺◌̖◌𐻿◌֚b; a◌᷺◌̖◌𐻿◌֚b; a◌᷺◌̖◌𐻿◌֚b; a◌᷺◌̖◌𐻿◌֚b; ) LATIN SMALL LETTER A, HEBREW ACCENT YETIV, COMBINING GRAVE ACCENT BELOW, COMBINING DOT BELOW LEFT, ARABIC SMALL LOW WORD MADDA, LATIN SMALL LETTER B +0061 10EFF 059A 0316 1DFA 0062;0061 1DFA 10EFF 0316 059A 0062;0061 1DFA 10EFF 0316 059A 0062;0061 1DFA 10EFF 0316 059A 0062;0061 1DFA 10EFF 0316 059A 0062; # (a◌𐻿◌֚◌̖◌᷺b; a◌᷺◌𐻿◌̖◌֚b; a◌᷺◌𐻿◌̖◌֚b; a◌᷺◌𐻿◌̖◌֚b; a◌᷺◌𐻿◌̖◌֚b; ) LATIN SMALL LETTER A, ARABIC SMALL LOW WORD MADDA, HEBREW ACCENT YETIV, COMBINING GRAVE ACCENT BELOW, COMBINING DOT BELOW LEFT, LATIN SMALL LETTER B 0061 059A 0316 1DFA 10F46 0062;0061 1DFA 0316 10F46 059A 0062;0061 1DFA 0316 10F46 059A 0062;0061 1DFA 0316 10F46 059A 0062;0061 1DFA 0316 10F46 059A 0062; # (a◌֚◌̖◌᷺◌𐽆b; a◌᷺◌̖◌𐽆◌֚b; a◌᷺◌̖◌𐽆◌֚b; a◌᷺◌̖◌𐽆◌֚b; a◌᷺◌̖◌𐽆◌֚b; ) LATIN SMALL LETTER A, HEBREW ACCENT YETIV, COMBINING GRAVE ACCENT BELOW, COMBINING DOT BELOW LEFT, SOGDIAN COMBINING DOT BELOW, LATIN SMALL LETTER B 0061 10F46 059A 0316 1DFA 0062;0061 1DFA 10F46 0316 059A 0062;0061 1DFA 10F46 0316 059A 0062;0061 1DFA 10F46 0316 059A 0062;0061 1DFA 10F46 0316 059A 0062; # (a◌𐽆◌֚◌̖◌᷺b; a◌᷺◌𐽆◌̖◌֚b; a◌᷺◌𐽆◌̖◌֚b; a◌᷺◌𐽆◌̖◌֚b; a◌᷺◌𐽆◌̖◌֚b; ) LATIN SMALL LETTER A, SOGDIAN COMBINING DOT BELOW, HEBREW ACCENT YETIV, COMBINING GRAVE ACCENT BELOW, COMBINING DOT BELOW LEFT, LATIN SMALL LETTER B 0061 059A 0316 1DFA 10F47 0062;0061 1DFA 0316 10F47 059A 0062;0061 1DFA 0316 10F47 059A 0062;0061 1DFA 0316 10F47 059A 0062;0061 1DFA 0316 10F47 059A 0062; # (a◌֚◌̖◌᷺◌𐽇b; a◌᷺◌̖◌𐽇◌֚b; a◌᷺◌̖◌𐽇◌֚b; a◌᷺◌̖◌𐽇◌֚b; a◌᷺◌̖◌𐽇◌֚b; ) LATIN SMALL LETTER A, HEBREW ACCENT YETIV, COMBINING GRAVE ACCENT BELOW, COMBINING DOT BELOW LEFT, SOGDIAN COMBINING TWO DOTS BELOW, LATIN SMALL LETTER B @@ -18640,6 +18708,10 @@ FFEE;FFEE;FFEE;25CB;25CB; # (￮; ￮; ￮; ○; ○; ) HALFWIDTH WHITE CIRCLE 0061 11D45 05B0 094D 3099 0062;0061 3099 11D45 094D 05B0 0062;0061 3099 11D45 094D 05B0 0062;0061 3099 11D45 094D 05B0 0062;0061 3099 11D45 094D 05B0 0062; # (a◌𑵅◌ְ◌्◌゙b; a◌゙◌𑵅◌्◌ְb; a◌゙◌𑵅◌्◌ְb; a◌゙◌𑵅◌्◌ְb; a◌゙◌𑵅◌्◌ְb; ) LATIN SMALL LETTER A, MASARAM GONDI VIRAMA, HEBREW POINT SHEVA, DEVANAGARI SIGN VIRAMA, COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK, LATIN SMALL LETTER B 0061 05B0 094D 3099 11D97 0062;0061 3099 094D 11D97 05B0 0062;0061 3099 094D 11D97 05B0 0062;0061 3099 094D 11D97 05B0 0062;0061 3099 094D 11D97 05B0 0062; # (a◌ְ◌्◌゙◌𑶗b; a◌゙◌्◌𑶗◌ְb; a◌゙◌्◌𑶗◌ְb; a◌゙◌्◌𑶗◌ְb; a◌゙◌्◌𑶗◌ְb; ) LATIN SMALL LETTER A, HEBREW POINT SHEVA, DEVANAGARI SIGN VIRAMA, COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK, GUNJALA GONDI VIRAMA, LATIN SMALL LETTER B 0061 11D97 05B0 094D 3099 0062;0061 3099 11D97 094D 05B0 0062;0061 3099 11D97 094D 05B0 0062;0061 3099 11D97 094D 05B0 0062;0061 3099 11D97 094D 05B0 0062; # (a◌𑶗◌ְ◌्◌゙b; a◌゙◌𑶗◌्◌ְb; a◌゙◌𑶗◌्◌ְb; a◌゙◌𑶗◌्◌ְb; a◌゙◌𑶗◌्◌ְb; ) LATIN SMALL LETTER A, GUNJALA GONDI VIRAMA, HEBREW POINT SHEVA, DEVANAGARI SIGN VIRAMA, COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK, LATIN SMALL LETTER B +0061 05B0 094D 3099 11F41 0062;0061 3099 094D 11F41 05B0 0062;0061 3099 094D 11F41 05B0 0062;0061 3099 094D 11F41 05B0 0062;0061 3099 094D 11F41 05B0 0062; # (a◌ְ◌्◌゙𑽁b; a◌゙◌्𑽁◌ְb; a◌゙◌्𑽁◌ְb; a◌゙◌्𑽁◌ְb; a◌゙◌्𑽁◌ְb; ) LATIN SMALL LETTER A, HEBREW POINT SHEVA, DEVANAGARI SIGN VIRAMA, COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK, KAWI SIGN KILLER, LATIN SMALL LETTER B +0061 11F41 05B0 094D 3099 0062;0061 3099 11F41 094D 05B0 0062;0061 3099 11F41 094D 05B0 0062;0061 3099 11F41 094D 05B0 0062;0061 3099 11F41 094D 05B0 0062; # (a𑽁◌ְ◌्◌゙b; a◌゙𑽁◌्◌ְb; a◌゙𑽁◌्◌ְb; a◌゙𑽁◌्◌ְb; a◌゙𑽁◌्◌ְb; ) LATIN SMALL LETTER A, KAWI SIGN KILLER, HEBREW POINT SHEVA, DEVANAGARI SIGN VIRAMA, COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK, LATIN SMALL LETTER B +0061 05B0 094D 3099 11F42 0062;0061 3099 094D 11F42 05B0 0062;0061 3099 094D 11F42 05B0 0062;0061 3099 094D 11F42 05B0 0062;0061 3099 094D 11F42 05B0 0062; # (a◌ְ◌्◌゙◌𑽂b; a◌゙◌्◌𑽂◌ְb; a◌゙◌्◌𑽂◌ְb; a◌゙◌्◌𑽂◌ְb; a◌゙◌्◌𑽂◌ְb; ) LATIN SMALL LETTER A, HEBREW POINT SHEVA, DEVANAGARI SIGN VIRAMA, COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK, KAWI CONJOINER, LATIN SMALL LETTER B +0061 11F42 05B0 094D 3099 0062;0061 3099 11F42 094D 05B0 0062;0061 3099 11F42 094D 05B0 0062;0061 3099 11F42 094D 05B0 0062;0061 3099 11F42 094D 05B0 0062; # (a◌𑽂◌ְ◌्◌゙b; a◌゙◌𑽂◌्◌ְb; a◌゙◌𑽂◌्◌ְb; a◌゙◌𑽂◌्◌ְb; a◌゙◌𑽂◌्◌ְb; ) LATIN SMALL LETTER A, KAWI CONJOINER, HEBREW POINT SHEVA, DEVANAGARI SIGN VIRAMA, COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK, LATIN SMALL LETTER B 0061 16FF0 0334 16AF0 0062;0061 0334 16AF0 16FF0 0062;0061 0334 16AF0 16FF0 0062;0061 0334 16AF0 16FF0 0062;0061 0334 16AF0 16FF0 0062; # (a𖿰◌̴◌𖫰b; a◌̴◌𖫰𖿰b; a◌̴◌𖫰𖿰b; a◌̴◌𖫰𖿰b; a◌̴◌𖫰𖿰b; ) LATIN SMALL LETTER A, VIETNAMESE ALTERNATE READING MARK CA, COMBINING TILDE OVERLAY, BASSA VAH COMBINING HIGH TONE, LATIN SMALL LETTER B 0061 16AF0 16FF0 0334 0062;0061 16AF0 0334 16FF0 0062;0061 16AF0 0334 16FF0 0062;0061 16AF0 0334 16FF0 0062;0061 16AF0 0334 16FF0 0062; # (a◌𖫰𖿰◌̴b; a◌𖫰◌̴𖿰b; a◌𖫰◌̴𖿰b; a◌𖫰◌̴𖿰b; a◌𖫰◌̴𖿰b; ) LATIN SMALL LETTER A, BASSA VAH COMBINING HIGH TONE, VIETNAMESE ALTERNATE READING MARK CA, COMBINING TILDE OVERLAY, LATIN SMALL LETTER B 0061 16FF0 0334 16AF1 0062;0061 0334 16AF1 16FF0 0062;0061 0334 16AF1 16FF0 0062;0061 0334 16AF1 16FF0 0062;0061 0334 16AF1 16FF0 0062; # (a𖿰◌̴◌𖫱b; a◌̴◌𖫱𖿰b; a◌̴◌𖫱𖿰b; a◌̴◌𖫱𖿰b; a◌̴◌𖫱𖿰b; ) LATIN SMALL LETTER A, VIETNAMESE ALTERNATE READING MARK CA, COMBINING TILDE OVERLAY, BASSA VAH COMBINING LOW TONE, LATIN SMALL LETTER B @@ -18812,6 +18884,8 @@ FFEE;FFEE;FFEE;25CB;25CB; # (￮; ￮; ￮; ○; ○; ) HALFWIDTH WHITE CIRCLE 0061 1E029 0315 0300 05AE 0062;0061 05AE 1E029 0300 0315 0062;0061 05AE 1E029 0300 0315 0062;0061 05AE 1E029 0300 0315 0062;0061 05AE 1E029 0300 0315 0062; # (a◌𞀩◌̕◌̀◌֮b; a◌֮◌𞀩◌̀◌̕b; a◌֮◌𞀩◌̀◌̕b; a◌֮◌𞀩◌̀◌̕b; a◌֮◌𞀩◌̀◌̕b; ) LATIN SMALL LETTER A, COMBINING GLAGOLITIC LETTER IOTATED BIG YUS, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, LATIN SMALL LETTER B 0061 0315 0300 05AE 1E02A 0062;00E0 05AE 1E02A 0315 0062;0061 05AE 0300 1E02A 0315 0062;00E0 05AE 1E02A 0315 0062;0061 05AE 0300 1E02A 0315 0062; # (a◌̕◌̀◌֮◌𞀪b; à◌֮◌𞀪◌̕b; a◌֮◌̀◌𞀪◌̕b; à◌֮◌𞀪◌̕b; a◌֮◌̀◌𞀪◌̕b; ) LATIN SMALL LETTER A, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, COMBINING GLAGOLITIC LETTER FITA, LATIN SMALL LETTER B 0061 1E02A 0315 0300 05AE 0062;0061 05AE 1E02A 0300 0315 0062;0061 05AE 1E02A 0300 0315 0062;0061 05AE 1E02A 0300 0315 0062;0061 05AE 1E02A 0300 0315 0062; # (a◌𞀪◌̕◌̀◌֮b; a◌֮◌𞀪◌̀◌̕b; a◌֮◌𞀪◌̀◌̕b; a◌֮◌𞀪◌̀◌̕b; a◌֮◌𞀪◌̀◌̕b; ) LATIN SMALL LETTER A, COMBINING GLAGOLITIC LETTER FITA, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, LATIN SMALL LETTER B +0061 0315 0300 05AE 1E08F 0062;00E0 05AE 1E08F 0315 0062;0061 05AE 0300 1E08F 0315 0062;00E0 05AE 1E08F 0315 0062;0061 05AE 0300 1E08F 0315 0062; # (a◌̕◌̀◌֮◌𞂏b; à◌֮◌𞂏◌̕b; a◌֮◌̀◌𞂏◌̕b; à◌֮◌𞂏◌̕b; a◌֮◌̀◌𞂏◌̕b; ) LATIN SMALL LETTER A, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I, LATIN SMALL LETTER B +0061 1E08F 0315 0300 05AE 0062;0061 05AE 1E08F 0300 0315 0062;0061 05AE 1E08F 0300 0315 0062;0061 05AE 1E08F 0300 0315 0062;0061 05AE 1E08F 0300 0315 0062; # (a◌𞂏◌̕◌̀◌֮b; a◌֮◌𞂏◌̀◌̕b; a◌֮◌𞂏◌̀◌̕b; a◌֮◌𞂏◌̀◌̕b; a◌֮◌𞂏◌̀◌̕b; ) LATIN SMALL LETTER A, COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, LATIN SMALL LETTER B 0061 0315 0300 05AE 1E130 0062;00E0 05AE 1E130 0315 0062;0061 05AE 0300 1E130 0315 0062;00E0 05AE 1E130 0315 0062;0061 05AE 0300 1E130 0315 0062; # (a◌̕◌̀◌֮◌𞄰b; à◌֮◌𞄰◌̕b; a◌֮◌̀◌𞄰◌̕b; à◌֮◌𞄰◌̕b; a◌֮◌̀◌𞄰◌̕b; ) LATIN SMALL LETTER A, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, NYIAKENG PUACHUE HMONG TONE-B, LATIN SMALL LETTER B 0061 1E130 0315 0300 05AE 0062;0061 05AE 1E130 0300 0315 0062;0061 05AE 1E130 0300 0315 0062;0061 05AE 1E130 0300 0315 0062;0061 05AE 1E130 0300 0315 0062; # (a◌𞄰◌̕◌̀◌֮b; a◌֮◌𞄰◌̀◌̕b; a◌֮◌𞄰◌̀◌̕b; a◌֮◌𞄰◌̀◌̕b; a◌֮◌𞄰◌̀◌̕b; ) LATIN SMALL LETTER A, NYIAKENG PUACHUE HMONG TONE-B, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, LATIN SMALL LETTER B 0061 0315 0300 05AE 1E131 0062;00E0 05AE 1E131 0315 0062;0061 05AE 0300 1E131 0315 0062;00E0 05AE 1E131 0315 0062;0061 05AE 0300 1E131 0315 0062; # (a◌̕◌̀◌֮◌𞄱b; à◌֮◌𞄱◌̕b; a◌֮◌̀◌𞄱◌̕b; à◌֮◌𞄱◌̕b; a◌֮◌̀◌𞄱◌̕b; ) LATIN SMALL LETTER A, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, NYIAKENG PUACHUE HMONG TONE-M, LATIN SMALL LETTER B @@ -18836,6 +18910,14 @@ FFEE;FFEE;FFEE;25CB;25CB; # (￮; ￮; ￮; ○; ○; ) HALFWIDTH WHITE CIRCLE 0061 1E2EE 0315 0300 05AE 0062;0061 05AE 1E2EE 0300 0315 0062;0061 05AE 1E2EE 0300 0315 0062;0061 05AE 1E2EE 0300 0315 0062;0061 05AE 1E2EE 0300 0315 0062; # (a◌𞋮◌̕◌̀◌֮b; a◌֮◌𞋮◌̀◌̕b; a◌֮◌𞋮◌̀◌̕b; a◌֮◌𞋮◌̀◌̕b; a◌֮◌𞋮◌̀◌̕b; ) LATIN SMALL LETTER A, WANCHO TONE KOI, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, LATIN SMALL LETTER B 0061 0315 0300 05AE 1E2EF 0062;00E0 05AE 1E2EF 0315 0062;0061 05AE 0300 1E2EF 0315 0062;00E0 05AE 1E2EF 0315 0062;0061 05AE 0300 1E2EF 0315 0062; # (a◌̕◌̀◌֮◌𞋯b; à◌֮◌𞋯◌̕b; a◌֮◌̀◌𞋯◌̕b; à◌֮◌𞋯◌̕b; a◌֮◌̀◌𞋯◌̕b; ) LATIN SMALL LETTER A, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, WANCHO TONE KOINI, LATIN SMALL LETTER B 0061 1E2EF 0315 0300 05AE 0062;0061 05AE 1E2EF 0300 0315 0062;0061 05AE 1E2EF 0300 0315 0062;0061 05AE 1E2EF 0300 0315 0062;0061 05AE 1E2EF 0300 0315 0062; # (a◌𞋯◌̕◌̀◌֮b; a◌֮◌𞋯◌̀◌̕b; a◌֮◌𞋯◌̀◌̕b; a◌֮◌𞋯◌̀◌̕b; a◌֮◌𞋯◌̀◌̕b; ) LATIN SMALL LETTER A, WANCHO TONE KOINI, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, LATIN SMALL LETTER B +0061 035C 0315 0300 1E4EC 0062;00E0 0315 1E4EC 035C 0062;0061 0300 0315 1E4EC 035C 0062;00E0 0315 1E4EC 035C 0062;0061 0300 0315 1E4EC 035C 0062; # (a◌͜◌̕◌̀◌𞓬b; à◌̕◌𞓬◌͜b; a◌̀◌̕◌𞓬◌͜b; à◌̕◌𞓬◌͜b; a◌̀◌̕◌𞓬◌͜b; ) LATIN SMALL LETTER A, COMBINING DOUBLE BREVE BELOW, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, NAG MUNDARI SIGN MUHOR, LATIN SMALL LETTER B +0061 1E4EC 035C 0315 0300 0062;00E0 1E4EC 0315 035C 0062;0061 0300 1E4EC 0315 035C 0062;00E0 1E4EC 0315 035C 0062;0061 0300 1E4EC 0315 035C 0062; # (a◌𞓬◌͜◌̕◌̀b; à◌𞓬◌̕◌͜b; a◌̀◌𞓬◌̕◌͜b; à◌𞓬◌̕◌͜b; a◌̀◌𞓬◌̕◌͜b; ) LATIN SMALL LETTER A, NAG MUNDARI SIGN MUHOR, COMBINING DOUBLE BREVE BELOW, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, LATIN SMALL LETTER B +0061 035C 0315 0300 1E4ED 0062;00E0 0315 1E4ED 035C 0062;0061 0300 0315 1E4ED 035C 0062;00E0 0315 1E4ED 035C 0062;0061 0300 0315 1E4ED 035C 0062; # (a◌͜◌̕◌̀◌𞓭b; à◌̕◌𞓭◌͜b; a◌̀◌̕◌𞓭◌͜b; à◌̕◌𞓭◌͜b; a◌̀◌̕◌𞓭◌͜b; ) LATIN SMALL LETTER A, COMBINING DOUBLE BREVE BELOW, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, NAG MUNDARI SIGN TOYOR, LATIN SMALL LETTER B +0061 1E4ED 035C 0315 0300 0062;00E0 1E4ED 0315 035C 0062;0061 0300 1E4ED 0315 035C 0062;00E0 1E4ED 0315 035C 0062;0061 0300 1E4ED 0315 035C 0062; # (a◌𞓭◌͜◌̕◌̀b; à◌𞓭◌̕◌͜b; a◌̀◌𞓭◌̕◌͜b; à◌𞓭◌̕◌͜b; a◌̀◌𞓭◌̕◌͜b; ) LATIN SMALL LETTER A, NAG MUNDARI SIGN TOYOR, COMBINING DOUBLE BREVE BELOW, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, LATIN SMALL LETTER B +0061 059A 0316 1DFA 1E4EE 0062;0061 1DFA 0316 1E4EE 059A 0062;0061 1DFA 0316 1E4EE 059A 0062;0061 1DFA 0316 1E4EE 059A 0062;0061 1DFA 0316 1E4EE 059A 0062; # (a◌֚◌̖◌᷺◌𞓮b; a◌᷺◌̖◌𞓮◌֚b; a◌᷺◌̖◌𞓮◌֚b; a◌᷺◌̖◌𞓮◌֚b; a◌᷺◌̖◌𞓮◌֚b; ) LATIN SMALL LETTER A, HEBREW ACCENT YETIV, COMBINING GRAVE ACCENT BELOW, COMBINING DOT BELOW LEFT, NAG MUNDARI SIGN IKIR, LATIN SMALL LETTER B +0061 1E4EE 059A 0316 1DFA 0062;0061 1DFA 1E4EE 0316 059A 0062;0061 1DFA 1E4EE 0316 059A 0062;0061 1DFA 1E4EE 0316 059A 0062;0061 1DFA 1E4EE 0316 059A 0062; # (a◌𞓮◌֚◌̖◌᷺b; a◌᷺◌𞓮◌̖◌֚b; a◌᷺◌𞓮◌̖◌֚b; a◌᷺◌𞓮◌̖◌֚b; a◌᷺◌𞓮◌̖◌֚b; ) LATIN SMALL LETTER A, NAG MUNDARI SIGN IKIR, HEBREW ACCENT YETIV, COMBINING GRAVE ACCENT BELOW, COMBINING DOT BELOW LEFT, LATIN SMALL LETTER B +0061 0315 0300 05AE 1E4EF 0062;00E0 05AE 1E4EF 0315 0062;0061 05AE 0300 1E4EF 0315 0062;00E0 05AE 1E4EF 0315 0062;0061 05AE 0300 1E4EF 0315 0062; # (a◌̕◌̀◌֮◌𞓯b; à◌֮◌𞓯◌̕b; a◌֮◌̀◌𞓯◌̕b; à◌֮◌𞓯◌̕b; a◌֮◌̀◌𞓯◌̕b; ) LATIN SMALL LETTER A, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, NAG MUNDARI SIGN SUTUH, LATIN SMALL LETTER B +0061 1E4EF 0315 0300 05AE 0062;0061 05AE 1E4EF 0300 0315 0062;0061 05AE 1E4EF 0300 0315 0062;0061 05AE 1E4EF 0300 0315 0062;0061 05AE 1E4EF 0300 0315 0062; # (a◌𞓯◌̕◌̀◌֮b; a◌֮◌𞓯◌̀◌̕b; a◌֮◌𞓯◌̀◌̕b; a◌֮◌𞓯◌̀◌̕b; a◌֮◌𞓯◌̀◌̕b; ) LATIN SMALL LETTER A, NAG MUNDARI SIGN SUTUH, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, LATIN SMALL LETTER B 0061 059A 0316 1DFA 1E8D0 0062;0061 1DFA 0316 1E8D0 059A 0062;0061 1DFA 0316 1E8D0 059A 0062;0061 1DFA 0316 1E8D0 059A 0062;0061 1DFA 0316 1E8D0 059A 0062; # (a◌֚◌̖◌᷺◌𞣐b; a◌᷺◌̖◌𞣐◌֚b; a◌᷺◌̖◌𞣐◌֚b; a◌᷺◌̖◌𞣐◌֚b; a◌᷺◌̖◌𞣐◌֚b; ) LATIN SMALL LETTER A, HEBREW ACCENT YETIV, COMBINING GRAVE ACCENT BELOW, COMBINING DOT BELOW LEFT, MENDE KIKAKUI COMBINING NUMBER TEENS, LATIN SMALL LETTER B 0061 1E8D0 059A 0316 1DFA 0062;0061 1DFA 1E8D0 0316 059A 0062;0061 1DFA 1E8D0 0316 059A 0062;0061 1DFA 1E8D0 0316 059A 0062;0061 1DFA 1E8D0 0316 059A 0062; # (a◌𞣐◌֚◌̖◌᷺b; a◌᷺◌𞣐◌̖◌֚b; a◌᷺◌𞣐◌̖◌֚b; a◌᷺◌𞣐◌̖◌֚b; a◌᷺◌𞣐◌̖◌֚b; ) LATIN SMALL LETTER A, MENDE KIKAKUI COMBINING NUMBER TEENS, HEBREW ACCENT YETIV, COMBINING GRAVE ACCENT BELOW, COMBINING DOT BELOW LEFT, LATIN SMALL LETTER B 0061 059A 0316 1DFA 1E8D1 0062;0061 1DFA 0316 1E8D1 059A 0062;0061 1DFA 0316 1E8D1 059A 0062;0061 1DFA 0316 1E8D1 059A 0062;0061 1DFA 0316 1E8D1 059A 0062; # (a◌֚◌̖◌᷺◌𞣑b; a◌᷺◌̖◌𞣑◌֚b; a◌᷺◌̖◌𞣑◌֚b; a◌᷺◌̖◌𞣑◌֚b; a◌᷺◌̖◌𞣑◌֚b; ) LATIN SMALL LETTER A, HEBREW ACCENT YETIV, COMBINING GRAVE ACCENT BELOW, COMBINING DOT BELOW LEFT, MENDE KIKAKUI COMBINING NUMBER TENS, LATIN SMALL LETTER B diff --git a/admin/unidata/PropertyValueAliases.txt b/admin/unidata/PropertyValueAliases.txt index bdc13857dc..9346fcf03e 100644 --- a/admin/unidata/PropertyValueAliases.txt +++ b/admin/unidata/PropertyValueAliases.txt @@ -1,11 +1,11 @@ -# PropertyValueAliases-14.0.0.txt -# Date: 2021-05-10, 21:08:53 GMT -# © 2021 Unicode®, Inc. +# PropertyValueAliases-15.0.0.txt +# Date: 2022-08-05, 23:42:17 GMT +# © 2022 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. -# For terms of use, see http://www.unicode.org/terms_of_use.html +# For terms of use, see https://www.unicode.org/terms_of_use.html # # Unicode Character Database -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see https://www.unicode.org/reports/tr44/ # # This file contains aliases for property values used in the UCD. # These names can be used for XML formats of UCD data, for regular-expression @@ -90,6 +90,7 @@ age; 12.0 ; V12_0 age; 12.1 ; V12_1 age; 13.0 ; V13_0 age; 14.0 ; V14_0 +age; 15.0 ; V15_0 age; NA ; Unassigned # Alphabetic (Alpha) @@ -135,7 +136,6 @@ Bidi_M; Y ; Yes ; T # Bidi_Mirroring_Glyph (bmg) -# @missing: 0000..10FFFF; Bidi_Mirroring_Glyph; # Bidi_Paired_Bracket (bpb) @@ -162,6 +162,7 @@ blk; Ancient_Symbols ; Ancient_Symbols blk; Arabic ; Arabic blk; Arabic_Ext_A ; Arabic_Extended_A blk; Arabic_Ext_B ; Arabic_Extended_B +blk; Arabic_Ext_C ; Arabic_Extended_C blk; Arabic_Math ; Arabic_Mathematical_Alphabetic_Symbols blk; Arabic_PF_A ; Arabic_Presentation_Forms_A ; Arabic_Presentation_Forms-A blk; Arabic_PF_B ; Arabic_Presentation_Forms_B @@ -206,6 +207,7 @@ blk; CJK_Ext_D ; CJK_Unified_Ideographs_Extension_D blk; CJK_Ext_E ; CJK_Unified_Ideographs_Extension_E blk; CJK_Ext_F ; CJK_Unified_Ideographs_Extension_F blk; CJK_Ext_G ; CJK_Unified_Ideographs_Extension_G +blk; CJK_Ext_H ; CJK_Unified_Ideographs_Extension_H blk; CJK_Radicals_Sup ; CJK_Radicals_Supplement blk; CJK_Strokes ; CJK_Strokes blk; CJK_Symbols ; CJK_Symbols_And_Punctuation @@ -223,10 +225,12 @@ blk; Cyrillic ; Cyrillic blk; Cyrillic_Ext_A ; Cyrillic_Extended_A blk; Cyrillic_Ext_B ; Cyrillic_Extended_B blk; Cyrillic_Ext_C ; Cyrillic_Extended_C +blk; Cyrillic_Ext_D ; Cyrillic_Extended_D blk; Cyrillic_Sup ; Cyrillic_Supplement ; Cyrillic_Supplementary blk; Deseret ; Deseret blk; Devanagari ; Devanagari blk; Devanagari_Ext ; Devanagari_Extended +blk; Devanagari_Ext_A ; Devanagari_Extended_A blk; Diacriticals ; Combining_Diacritical_Marks blk; Diacriticals_Ext ; Combining_Diacritical_Marks_Extended blk; Diacriticals_For_Symbols ; Combining_Diacritical_Marks_For_Symbols; Combining_Marks_For_Symbols @@ -288,6 +292,7 @@ blk; Jamo_Ext_A ; Hangul_Jamo_Extended_A blk; Jamo_Ext_B ; Hangul_Jamo_Extended_B blk; Javanese ; Javanese blk; Kaithi ; Kaithi +blk; Kaktovik_Numerals ; Kaktovik_Numerals blk; Kana_Ext_A ; Kana_Extended_A blk; Kana_Ext_B ; Kana_Extended_B blk; Kana_Sup ; Kana_Supplement @@ -296,6 +301,7 @@ blk; Kangxi ; Kangxi_Radicals blk; Kannada ; Kannada blk; Katakana ; Katakana blk; Katakana_Ext ; Katakana_Phonetic_Extensions +blk; Kawi ; Kawi blk; Kayah_Li ; Kayah_Li blk; Kharoshthi ; Kharoshthi blk; Khitan_Small_Script ; Khitan_Small_Script @@ -360,6 +366,7 @@ blk; Myanmar ; Myanmar blk; Myanmar_Ext_A ; Myanmar_Extended_A blk; Myanmar_Ext_B ; Myanmar_Extended_B blk; Nabataean ; Nabataean +blk; Nag_Mundari ; Nag_Mundari blk; Nandinagari ; Nandinagari blk; NB ; No_Block blk; New_Tai_Lue ; New_Tai_Lue @@ -663,7 +670,6 @@ EPres; Y ; Yes ; T # Equivalent_Unified_Ideograph (EqUIdeo) -# @missing: 0000..10FFFF; Equivalent_Unified_Ideograph; # Expands_On_NFC (XO_NFC) @@ -1143,7 +1149,6 @@ NFD_QC; Y ; Yes # NFKC_Casefold (NFKC_CF) -# @missing: 0000..10FFFF; NFKC_Casefold; # NFKC_Quick_Check (NFKC_QC) @@ -1313,6 +1318,7 @@ sc ; Ital ; Old_Italic sc ; Java ; Javanese sc ; Kali ; Kayah_Li sc ; Kana ; Katakana +sc ; Kawi ; Kawi sc ; Khar ; Kharoshthi sc ; Khmr ; Khmer sc ; Khoj ; Khojki @@ -1345,6 +1351,7 @@ sc ; Mroo ; Mro sc ; Mtei ; Meetei_Mayek sc ; Mult ; Multani sc ; Mymr ; Myanmar +sc ; Nagm ; Nag_Mundari sc ; Nand ; Nandinagari sc ; Narb ; Old_North_Arabian sc ; Nbat ; Nabataean @@ -1418,7 +1425,6 @@ sc ; Zzzz ; Unknown # Script_Extensions (scx) -# @missing: 0000..10FFFF; Script_Extensions;